Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3634 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.9683. Min Act: -0.0000

Data Index: 1467253 (Python Code)

Max Activating Token Index: 882

Text #1

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.9399. Min Act: -0.0000

Data Index: 1457072 (Python Code)

Max Activating Token Index: 760

Text #2

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.0489. Min Act: -0.0000

Data Index: 1640462 (Python Code)

Max Activating Token Index: 236

Text #3

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.1747. Min Act: -0.0000

Data Index: 1439967 (Python Code)

Max Activating Token Index: 664

Text #4

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.3397. Min Act: -0.0000

Data Index: 1501933 (Python Code)

Max Activating Token Index: 362

Text #5

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.2679. Min Act: -0.0000

Data Index: 1494355 (Python Code)

Max Activating Token Index: 832

Text #6

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.2274. Min Act: -0.0000

Data Index: 1533309 (Python Code)

Max Activating Token Index: 509

Text #7

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.2479. Min Act: -0.0000

Data Index: 1542519 (Python Code)

Max Activating Token Index: 377

Text #8

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.2282. Min Act: -0.0000

Data Index: 1590249 (Python Code)

Max Activating Token Index: 761

Text #9

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.0124. Min Act: -0.0000

Data Index: 1427647 (Python Code)

Max Activating Token Index: 257

Text #10

Max Range: 1.9683. Min Range: -1.9683

Max Act: 0.9541. Min Act: -0.0000

Data Index: 1390133 (Python Code)

Max Activating Token Index: 512

Text #11

Max Range: 1.9683. Min Range: -1.9683

Max Act: 0.9365. Min Act: -0.0000

Data Index: 1566179 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.0009. Min Act: -0.0000

Data Index: 1440187 (Python Code)

Max Activating Token Index: 443

Text #13

Max Range: 1.9683. Min Range: -1.9683

Max Act: 0.8889. Min Act: -0.0000

Data Index: 1402179 (Python Code)

Max Activating Token Index: 578

Text #14

Max Range: 1.9683. Min Range: -1.9683

Max Act: 0.9077. Min Act: -0.0000

Data Index: 1651308 (Python Code)

Max Activating Token Index: 421

Text #15

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.0021. Min Act: -0.0000

Data Index: 754192 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 1.9683. Min Range: -1.9683

Max Act: 0.8973. Min Act: -0.0000

Data Index: 1647588 (Python Code)

Max Activating Token Index: 430

Text #17

Max Range: 1.9683. Min Range: -1.9683

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1587304 (Python Code)

Max Activating Token Index: 474

Text #18

Max Range: 1.9683. Min Range: -1.9683

Max Act: 0.9148. Min Act: -0.0000

Data Index: 1588728 (Python Code)

Max Activating Token Index: 220

Text #19

Max Range: 1.9683. Min Range: -1.9683

Max Act: 0.8314. Min Act: -0.0000

Data Index: 1482672 (Python Code)

Max Activating Token Index: 158